arXiv subjects

Vyom Sharma

Publications and source records attributed to Vyom Sharma.

4 recordsLinked to original sources

arXiv2026

RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts

The optimal kernel configuration for Mixture-of-Experts (MoE) inference depends on both batch size and the expert routing distribution, yet production systems dispatch from batch size alone, leaving 10-70% of kernel throughput unrealized. We present RaMP, a routing-aware dispatch framework. A performance-region analysis derives, from hardware constants alone, when each optimization helps, correctly predicting all 8 tested architectures, including 3 unseen. A four-parameter wave cost model selects the fastest configuration from the runtime expert histogram, achieving 0.93% mean regret versus exhaustive search, fitted from just 10-24 minutes of one-time profiling per model. Because the model depends only on CTA grid geometry, it is kernel-agnostic: applied to Alpha-MoE, it delivers 1.14x with no source modification. Paired with a co-designed CuTe DSL kernel exposing 134-268 polymorphic configurations, RaMP delivers 1.22x kernel speedup over static dispatch and 1.30x end-to-end speedup in vLLM serving over Triton, 1.41x over DeepGEMM, and 1.13x over FlashInfer CUTLASS.

cs.LG↗

arXiv2026

ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection

Long-context inference is constrained by KV-cache memory, which grows linearly with sequence length; KV-cache compression therefore hinges on reliably selecting which past tokens to retain. Most geometry-based eviction methods score keys by cosine similarity to a global centroid, but cosine is scale-invariant and can discard magnitude cues that distinguish semantically salient tokens. We propose ManifoldKV, a training-free scorer that ranks tokens by Euclidean distance to the key centroid, capturing both angular and radial deviations. On the RULER benchmark, ManifoldKV achieves 95.7% accuracy at 4K-16K contexts with 20% compression; matching the best geometric baseline while improving robustness in two regimes where cosine scoring fails. First, on multi-key retrieval, ManifoldKV reduces directional collisions, achieving 92.4% vs KeyDiff's 77.0% (+15.4 points) on 3-key NIAH at 50% compression. Second, to address dilution and performance collapse of global centroids at 64K context, we introduce WindowedManifoldKV, which restores accuracy to 84.3% at 25% compression, a 49-point recovery over global L2 and +3.2 points over KeyDiff. The method requires only 3 lines of code and works across 4 architectures without tuning.

cs.LG↗

arXiv2023

A data science platform to enable time-domain astronomy

SkyPortal is an open-source software package designed to efficiently discover interesting transients, manage follow-up, perform characterization, and visualize the results. By enabling fast access to archival and catalog data, cross-matching heterogeneous data streams, and the triggering and monitoring of on-demand observations for further characterization, a SkyPortal-based platform has been operating at scale for 2 yr for the Zwicky Transient Facility Phase II community, with hundreds of users, containing tens of millions of time-domain sources, interacting with dozens of telescopes, and enabling community reporting. While SkyPortal emphasizes rich user experiences (UX) across common frontend workflows, recognizing that scientific inquiry is increasingly performed programmatically, SkyPortal also surfaces an extensive and well-documented API system. From backend and frontend software to data science analysis tools and visualization frameworks, the SkyPortal design emphasizes the re-use and leveraging of best-in-class approaches, with a strong extensibility ethos. For instance, SkyPortal now leverages ChatGPT large-language models (LLMs) to automatically generate and surface source-level human-readable summaries. With the imminent re-start of the next-generation of gravitational wave detectors, SkyPortal now also includes dedicated multi-messenger features addressing the requirements of rapid multi-messenger follow-up: multi-telescope management, team/group organizing interfaces, and cross-matching of multi-messenger data streams with time-domain optical surveys, with interfaces sufficiently intuitive for the newcomers to the field. (abridged)

astro-ph.IM↗

arXiv2023

Rehabilitation Exercise Repetition Segmentation and Counting using Skeletal Body Joints

Physical exercise is an essential component of rehabilitation programs that improve quality of life and reduce mortality and re-hospitalization rates. In AI-driven virtual rehabilitation programs, patients complete their exercises independently at home, while AI algorithms analyze the exercise data to provide feedback to patients and report their progress to clinicians. To analyze exercise data, the first step is to segment it into consecutive repetitions. There has been a significant amount of research performed on segmenting and counting the repetitive activities of healthy individuals using raw video data, which raises concerns regarding privacy and is computationally intensive. Previous research on patients' rehabilitation exercise segmentation relied on data collected by multiple wearable sensors, which are difficult to use at home by rehabilitation patients. Compared to healthy individuals, segmenting and counting exercise repetitions in patients is more challenging because of the irregular repetition duration and the variation between repetitions. This paper presents a novel approach for segmenting and counting the repetitions of rehabilitation exercises performed by patients, based on their skeletal body joints. Skeletal body joints can be acquired through depth cameras or computer vision techniques applied to RGB videos of patients. Various sequential neural networks are designed to analyze the sequences of skeletal body joints and perform repetition segmentation and counting. Extensive experiments on three publicly available rehabilitation exercise datasets, KIMORE, UI-PRMD, and IntelliRehabDS, demonstrate the superiority of the proposed method compared to previous methods. The proposed method enables accurate exercise analysis while preserving privacy, facilitating the effective delivery of virtual rehabilitation programs.

cs.CV↗